Semi-supervised learning has emerged as a popular framework for improving modeling accuracy while controlling labeling cost. Based on an extension of stochastic composite likeliho...
Joshua Dillon, Krishnakumar Balasubramanian, Guy L...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
: The paper proposes a different approach to data modeling. Analogous to the rejection method, where the misclassifications are removed and manually evaluated, we focus here on dif...
Abstract--This paper is concerned with the automatic recognition of dialogue acts (DAs) in multiparty conversational speech. We present a joint generative model for DA recognition ...
This paper proposes a state based approach to gesture learning and recognition. Using spatial clustering and temporal alignment, each gesture is defined to be an ordered sequence ...